© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 9954
    Prev
    Next
    INDEX
    Explanations

    news or updates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Scientific
    0.54
     empirical
    0.52
     systematic
    0.52
     scientific
    0.51
     quantitative
    0.49
    <0xC2>
    0.48
     underlying
    0.45
     constraint
    0.45
    h
    0.44
     <
    0.44
    POSITIVE LOGITS
    Новости
    0.74
    Newsletter
    0.63
     notizie
    0.55
    Upcoming
    0.54
     관광
    0.54
    𝙖
    0.54
    Prices
    0.53
    Restaurants
    0.53
    新闻
    0.52
    समाचार
    0.52
    Activations Density 0.004%

    No Known Activations